# workload_profile

> Workload profile benchmark workloads: Workload profile: Cache Intensive, Workload profile: CI/CD Build and 6 more.

Workload profile

## Workload profile: Cache Intensive {#workload_profile-cache}

Precomputed compound score for Cache Intensive workloads. A weighted average (geometric mean) of benchmark scores compared to their medians: score = ∏ (x\_i / m\_i)^(w\_i / Σw). The score of 1.0 represents a synthetic baseline server with the median performance of each component benchmark; 0.5 means roughly half the performance; and 2.0 means twice the performance of that reference profile. Component weights: 50% Redis RPS (pipeline=1, SET), 20% Redis RPS (pipeline=16, SET), 10% PassMark Memory Mark (composite), 10% Memory bandwidth (read, 16 MB ~ L3), 10% PassMark single-thread CPU. Rationale for component selection: In-memory key-value store workload, mixing direct Redis performance metrics with memory speed and latency benchmarks, and single-core CPU performance profiles.

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>workload_profile:cache</code></dd><dt>Unit of measurement</dt><dd>—</dd><dt>Server types evaluated</dt><dd>3,735</dd><dt>Total measurements</dt><dd>3,735</dd><dt>Range of measurements</dt><dd>0.011 – 15</dd><dt>Better</dt><dd>↑ Higher is better</dd></dl>

Components

| Component | Benchmark | Configuration | Weight |
| --- | --- | --- | --- |
| Redis RPS (pipeline=1, SET) | [`redis:rps-extrapolated`](https://docs.sparecores.com/benchmarks/redis.md#redis-rps-extrapolated) | `pipeline=1` `operation=SET` | 50% |
| Redis RPS (pipeline=16, SET) | [`redis:rps-extrapolated`](https://docs.sparecores.com/benchmarks/redis.md#redis-rps-extrapolated) | `pipeline=16` `operation=SET` | 20% |
| PassMark Memory Mark (composite) | [`passmark:memory_mark`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-memory_mark) | — | 10% |
| Memory bandwidth (read, 16 MB ~ L3) | [`bw_mem`](https://docs.sparecores.com/benchmarks/bw_mem.md#bw_mem) | `size=16` `operation=rd` | 10% |
| PassMark single-thread CPU | [`passmark:cpu_single_threaded_test`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_single_threaded_test) | — | 10% |

Score distribution <small>(3,735 measurements)</small>

![Score distribution of Workload profile: Cache Intensive](/benchmarks/histograms/workload_profile-cache.svg)

## Workload profile: CI/CD Build {#workload_profile-cicd}

Precomputed compound score for CI/CD Build workloads. A weighted average (geometric mean) of benchmark scores compared to their medians: score = ∏ (x\_i / m\_i)^(w\_i / Σw). The score of 1.0 represents a synthetic baseline server with the median performance of each component benchmark; 0.5 means roughly half the performance; and 2.0 means twice the performance of that reference profile. Component weights: 50% Geekbench Clang compilation (multi-core), 10% Geekbench Clang compilation (single-core), 20% stress-ng div16 best-N cores, 5% PassMark integer math, 5% PassMark compression, 5% Brotli compression (multi-core, level 0), 5% PassMark string sorting. Rationale for component selection: Build performance is mainly driven by multi-core compilation throughput, but also bundles single-core compilation speed and general CPU performance, multi-core compression and text/scripting processing.

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>workload_profile:cicd</code></dd><dt>Unit of measurement</dt><dd>—</dd><dt>Server types evaluated</dt><dd>3,742</dd><dt>Total measurements</dt><dd>3,742</dd><dt>Range of measurements</dt><dd>0.0085 – 18</dd><dt>Better</dt><dd>↑ Higher is better</dd></dl>

Components

| Component | Benchmark | Configuration | Weight |
| --- | --- | --- | --- |
| Geekbench Clang compilation (multi-core) | [`geekbench:clang`](https://docs.sparecores.com/benchmarks/geekbench.md#geekbench-clang) | `cores=multi` | 50% |
| Geekbench Clang compilation (single-core) | [`geekbench:clang`](https://docs.sparecores.com/benchmarks/geekbench.md#geekbench-clang) | `cores=single` | 10% |
| stress-ng div16 best-N cores | [`stress_ng:bestn`](https://docs.sparecores.com/benchmarks/stress_ng.md#stress_ng-bestn) | — | 20% |
| PassMark integer math | [`passmark:cpu_integer_maths_test`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_integer_maths_test) | — | 5% |
| PassMark compression | [`passmark:cpu_compression_test`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_compression_test) | — | 5% |
| Brotli compression (multi-core, level 0) | [`compression_text:compress`](https://docs.sparecores.com/benchmarks/compression_text.md#compression_text-compress) | `algo=brotli` `cores=single` `compression_level=0` | 5% |
| PassMark string sorting | [`passmark:cpu_string_sorting_test`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_string_sorting_test) | — | 5% |

Score distribution <small>(3,742 measurements)</small>

![Score distribution of Workload profile: CI/CD Build](/benchmarks/histograms/workload_profile-cicd.svg)

## Workload profile: Compute Heavy Applications {#workload_profile-compute}

Precomputed compound score for Compute Heavy Applications workloads. A weighted average (geometric mean) of benchmark scores compared to their medians: score = ∏ (x\_i / m\_i)^(w\_i / Σw). The score of 1.0 represents a synthetic baseline server with the median performance of each component benchmark; 0.5 means roughly half the performance; and 2.0 means twice the performance of that reference profile. Component weights: 15% stress-ng div16 best-N cores, 10% stress-ng div16 single core, 20% PassMark CPU Mark (composite), 10% Memory bandwidth (read, 64 MB), 15% PassMark floating point, 15% PassMark AVX/SSE/FMA (SIMD), 10% PassMark integer math, 5% PassMark physics simulation. Rationale for component selection: Number-crunching workload augmenting raw CPU performance stressing, general CPU performance benchmarks, memory bandwidth, and pure math computation speed like floating point, integer, SIMD (AVX/SSE/FMA) operations.

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>workload_profile:compute</code></dd><dt>Unit of measurement</dt><dd>—</dd><dt>Server types evaluated</dt><dd>3,742</dd><dt>Total measurements</dt><dd>3,742</dd><dt>Range of measurements</dt><dd>0.011 – 16</dd><dt>Better</dt><dd>↑ Higher is better</dd></dl>

Components

| Component | Benchmark | Configuration | Weight |
| --- | --- | --- | --- |
| stress-ng div16 best-N cores | [`stress_ng:bestn`](https://docs.sparecores.com/benchmarks/stress_ng.md#stress_ng-bestn) | — | 15% |
| stress-ng div16 single core | [`stress_ng:best1`](https://docs.sparecores.com/benchmarks/stress_ng.md#stress_ng-best1) | — | 10% |
| PassMark CPU Mark (composite) | [`passmark:cpu_mark`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_mark) | — | 20% |
| Memory bandwidth (read, 64 MB) | [`bw_mem`](https://docs.sparecores.com/benchmarks/bw_mem.md#bw_mem) | `size=64` `operation=rd` | 10% |
| PassMark floating point | [`passmark:cpu_floating_point_maths_test`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_floating_point_maths_test) | — | 15% |
| PassMark AVX/SSE/FMA (SIMD) | [`passmark:cpu_extended_instructions_test`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_extended_instructions_test) | — | 15% |
| PassMark integer math | [`passmark:cpu_integer_maths_test`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_integer_maths_test) | — | 10% |
| PassMark physics simulation | [`passmark:cpu_physics_test`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_physics_test) | — | 5% |

Score distribution <small>(3,742 measurements)</small>

![Score distribution of Workload profile: Compute Heavy Applications](/benchmarks/histograms/workload_profile-compute.svg)

## Workload profile: Data Analysis {#workload_profile-data_analysis}

Precomputed compound score for Data Analysis workloads. A weighted average (geometric mean) of benchmark scores compared to their medians: score = ∏ (x\_i / m\_i)^(w\_i / Σw). The score of 1.0 represents a synthetic baseline server with the median performance of each component benchmark; 0.5 means roughly half the performance; and 2.0 means twice the performance of that reference profile. Component weights: 70% PassMark CPU Mark (composite), 10% Gzip compression (single-core, level 5), 10% Memory bandwidth (read, 64 MB), 10% PassMark Memory Mark (composite). Rationale for component selection: Data analysis and ETL workloads are memory-bandwidth-bound and CPU-throughput-driven. The profile combines general CPU performance and memory bandwidth/latency as the primary drivers, supplemented by single-core compression speed as a proxy for serialisation-heavy ETL tasks.

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>workload_profile:data_analysis</code></dd><dt>Unit of measurement</dt><dd>—</dd><dt>Server types evaluated</dt><dd>3,711</dd><dt>Total measurements</dt><dd>3,711</dd><dt>Range of measurements</dt><dd>0.013 – 6.3</dd><dt>Better</dt><dd>↑ Higher is better</dd></dl>

Components

| Component | Benchmark | Configuration | Weight |
| --- | --- | --- | --- |
| PassMark CPU Mark (composite) | [`passmark:cpu_mark`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_mark) | — | 70% |
| Gzip compression (single-core, level 5) | [`compression_text:compress`](https://docs.sparecores.com/benchmarks/compression_text.md#compression_text-compress) | `algo=gzip` `cores=single` `compression_level=5` | 10% |
| Memory bandwidth (read, 64 MB) | [`bw_mem`](https://docs.sparecores.com/benchmarks/bw_mem.md#bw_mem) | `size=64` `operation=rd` | 10% |
| PassMark Memory Mark (composite) | [`passmark:memory_mark`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-memory_mark) | — | 10% |

Score distribution <small>(3,711 measurements)</small>

![Score distribution of Workload profile: Data Analysis](/benchmarks/histograms/workload_profile-data_analysis.svg)

## Workload profile: Relational Database inactive {#workload_profile-database}

Precomputed compound score for Relational Database workloads. A weighted average of normalised scores, each normalised to \[0, 1\] across all servers in the dataset. Component weights: 35% PassMark in-memory DB operations, 30% PassMark memory latency (512 MB), 20% PassMark Memory Mark (composite), 15% PassMark single-thread CPU. Rationale for component selection: Relational database workload (PostgreSQL, MySQL, transactional OLTP). Direct DB operation throughput is the primary driver, followed by memory latency for index lookups and buffer pool access, memory subsystem performance for working-set throughput, and single-thread CPU for query execution.

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>workload_profile:database</code></dd><dt>Unit of measurement</dt><dd>—</dd><dt>Server types evaluated</dt><dd>—</dd><dt>Total measurements</dt><dd>—</dd><dt>Range of measurements</dt><dd>—</dd><dt>Better</dt><dd>↑ Higher is better</dd></dl>

## Workload profile: LLM Inference {#workload_profile-llm}

Precomputed compound score for LLM Inference workloads. A weighted average (geometric mean) of benchmark scores compared to their medians: score = ∏ (x\_i / m\_i)^(w\_i / Σw). The score of 1.0 represents a synthetic baseline server with the median performance of each component benchmark; 0.5 means roughly half the performance; and 2.0 means twice the performance of that reference profile. Component weights: 15% LLM text generation (SmolLM-135M, 128 tok), 15% LLM prompt processing (SmolLM-135M, 512 tok), 15% LLM text generation (Llama 7B, 128 tok), 15% LLM prompt processing (Llama 7B, 512 tok), 15% LLM text generation (Llama-3.3 70B, 128 tok), 15% LLM prompt processing (Llama-3.3 70B, 512 tok), 5% Memory bandwidth (read, 256 MB), 2% PassMark AVX/SSE/FMA (SIMD), 2% PassMark floating point. Rationale for component selection: VRAM and memory-bandwidth-bound LLM inference workload, using direct LLM speed benchmarks at three model sizes, and supplementing with raw memory bandwidth and SIMD performance benchmarks.

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>workload_profile:llm</code></dd><dt>Unit of measurement</dt><dd>—</dd><dt>Server types evaluated</dt><dd>3,416</dd><dt>Total measurements</dt><dd>3,416</dd><dt>Range of measurements</dt><dd>0.0045 – 19</dd><dt>Better</dt><dd>↑ Higher is better</dd></dl>

Components

| Component | Benchmark | Configuration | Weight |
| --- | --- | --- | --- |
| LLM text generation (SmolLM-135M, 128 tok) | [`llm_speed:text_generation`](https://docs.sparecores.com/benchmarks/llm_speed.md#llm_speed-text_generation) | `model=SmolLM-135M.Q4_K_M.gguf` `tokens=128` | 15% |
| LLM prompt processing (SmolLM-135M, 512 tok) | [`llm_speed:prompt_processing`](https://docs.sparecores.com/benchmarks/llm_speed.md#llm_speed-prompt_processing) | `model=SmolLM-135M.Q4_K_M.gguf` `tokens=512` | 15% |
| LLM text generation (Llama 7B, 128 tok) | [`llm_speed:text_generation`](https://docs.sparecores.com/benchmarks/llm_speed.md#llm_speed-text_generation) | `model=llama-7b.Q4_K_M.gguf` `tokens=128` | 15% |
| LLM prompt processing (Llama 7B, 512 tok) | [`llm_speed:prompt_processing`](https://docs.sparecores.com/benchmarks/llm_speed.md#llm_speed-prompt_processing) | `model=llama-7b.Q4_K_M.gguf` `tokens=512` | 15% |
| LLM text generation (Llama-3.3 70B, 128 tok) | [`llm_speed:text_generation`](https://docs.sparecores.com/benchmarks/llm_speed.md#llm_speed-text_generation) | `model=Llama-3.3-70B-Instruct-Q4_K_M.gguf` `tokens=128` | 15% |
| LLM prompt processing (Llama-3.3 70B, 512 tok) | [`llm_speed:prompt_processing`](https://docs.sparecores.com/benchmarks/llm_speed.md#llm_speed-prompt_processing) | `model=Llama-3.3-70B-Instruct-Q4_K_M.gguf` `tokens=512` | 15% |
| Memory bandwidth (read, 256 MB) | [`bw_mem`](https://docs.sparecores.com/benchmarks/bw_mem.md#bw_mem) | `size=256` `operation=rd` | 5% |
| PassMark AVX/SSE/FMA (SIMD) | [`passmark:cpu_extended_instructions_test`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_extended_instructions_test) | — | 3% |
| PassMark floating point | [`passmark:cpu_floating_point_maths_test`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_floating_point_maths_test) | — | 3% |

Score distribution <small>(3,416 measurements)</small>

![Score distribution of Workload profile: LLM Inference](/benchmarks/histograms/workload_profile-llm.svg)

## Workload profile: ML inference inactive {#workload_profile-ml}

Precomputed compound score for CPU-based machine-learning inference workloads. A weighted average of normalised scores, each normalised to \[0, 1\] across all servers in the dataset. Component weights: 20% LLM text generation (llama-7b, 128 tokens), 15% memory bandwidth read (256 MB, bw\_mem), 10% LLM prompt processing (llama-7b, 512 tokens), 10% LLM text generation (gemma-2b, 128 tokens), 10% PassMark Memory Mark (composite), 10% PassMark AVX/SSE/FMA (SIMD), 10% Geekbench object detection (multi-core), 5% PassMark floating point, 5% Geekbench background blur (multi-core), 5% Geekbench structure-from-motion (multi-core).

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>workload_profile:ml</code></dd><dt>Unit of measurement</dt><dd>—</dd><dt>Server types evaluated</dt><dd>—</dd><dt>Total measurements</dt><dd>—</dd><dt>Range of measurements</dt><dd>—</dd><dt>Better</dt><dd>↑ Higher is better</dd></dl>

## Workload profile: Web Server {#workload_profile-web}

Precomputed compound score for Web Server workloads. A weighted average (geometric mean) of benchmark scores compared to their medians: score = ∏ (x\_i / m\_i)^(w\_i / Σw). The score of 1.0 represents a synthetic baseline server with the median performance of each component benchmark; 0.5 means roughly half the performance; and 2.0 means twice the performance of that reference profile. Component weights: 30% Static web RPS (1 KiB, 8 conn/vCPU), 20% Static web RPS (64 KiB, 8 conn/vCPU), 20% Static web throughput (256 KiB, 8 conn/vCPU), 20% OpenSSL AES-256-CBC (16 kB blocks), 5% Gzip compression (multi-core, level 5), 5% PassMark string sorting. Rationale for component selection: Primary workloads drivers are single-process static HTTP serving speed and throughput, text processing, TLS termination, and asset compression.

Benchmark details<dl><dt>Benchmark ID</dt><dd><code>workload_profile:web</code></dd><dt>Unit of measurement</dt><dd>—</dd><dt>Server types evaluated</dt><dd>3,738</dd><dt>Total measurements</dt><dd>3,738</dd><dt>Range of measurements</dt><dd>0.011 – 13</dd><dt>Better</dt><dd>↑ Higher is better</dd></dl>

Components

| Component | Benchmark | Configuration | Weight |
| --- | --- | --- | --- |
| Static web RPS (1 KiB, 8 conn/vCPU) | [`static_web:rps-extrapolated`](https://docs.sparecores.com/benchmarks/static_web.md#static_web-rps-extrapolated) | `size=1k` `connections_per_vcpus=8` | 30% |
| Static web RPS (64 KiB, 8 conn/vCPU) | [`static_web:rps-extrapolated`](https://docs.sparecores.com/benchmarks/static_web.md#static_web-rps-extrapolated) | `size=64k` `connections_per_vcpus=8` | 20% |
| Static web throughput (256 KiB, 8 conn/vCPU) | [`static_web:throughput-extrapolated`](https://docs.sparecores.com/benchmarks/static_web.md#static_web-throughput-extrapolated) | `size=256k` `connections_per_vcpus=8` | 20% |
| OpenSSL AES-256-CBC (16 kB blocks) | [`openssl`](https://docs.sparecores.com/benchmarks/openssl.md#openssl) | `algo=AES-256-CBC` `block_size=16384` | 20% |
| Gzip compression (multi-core, level 5) | [`compression_text:compress`](https://docs.sparecores.com/benchmarks/compression_text.md#compression_text-compress) | `algo=gzip` `cores=multi` `compression_level=5` | 5% |
| PassMark string sorting | [`passmark:cpu_string_sorting_test`](https://docs.sparecores.com/benchmarks/passmark.md#passmark-cpu_string_sorting_test) | — | 5% |

Score distribution <small>(3,738 measurements)</small>

![Score distribution of Workload profile: Web Server](/benchmarks/histograms/workload_profile-web.svg)
